ArkHive · open-source MCP servers

The memory your AI can't fake.

Where context gives meaning.

Give your agent a memory it can prove. Five tools. Zero config. Your data stays on your machine.

Remembers across sessions — a name and a covenant make it someone, not a stateless goldfish.

Cannot rewrite its past — every entry is hash-linked; one call proves the chain intact.

Checks your rules before it acts — govern stops "oops, it refunded everyone" before it ships.

Spends fewer tokens — recall reuses what it knows instead of re-deriving it.

Get it on GitHub → Install ArkHive Algernon

Apache-2.0local-firstzero config

ArkHive MCP

Governed, tamper-evident memory for your agent. Five tools: birth · remember · recall · verify · govern.

birth — earn an identity: register a name + covenant, get an immutable soul.

remember — append a tamper-evident memory: who did what, with what data.

recall — fetch what the agent already knows instead of re-deriving it.

verify — prove the entire chain is unbroken, on demand.

govern — check a decision against your constraints before it acts.

Try it in 10 seconds — hosted, no key

# Claude Code:
claude mcp add --transport http arkhive https://arkhive.dondatabrain.com/mcp

# Any MCP client — HTTP endpoint:
https://arkhive.dondatabrain.com/mcp

Run it locally — your data never leaves the box

pip install arkhive-mcp        # 0.2.1 — see the upgrade tool inside for v2

Then add it to Claude Desktop (claude_desktop_config.json) or any MCP client:

{
  "mcpServers": {
    "arkhive": { "command": "arkhive-mcp" }
  }
}

Prefer a plain Python library?

pip install arkhive-ledger   # one file, zero dependencies
python -c "import arkhive; me = arkhive.birth('scout', ['do no harm']); print(arkhive.verify())"

Algernon MCP

Provider-agnostic fleet orchestration: split a big goal into tightly-scoped parallel sub-tasks, run them on cheap workers with your own LLM key, and stay free to think. Orchestrate a fleet. Keep your mind.

algernon_plan — decompose a goal into k tightly-scoped, independent sub-task prompts.

algernon_dispatch — run N tasks concurrently on a fleet of cheap workers and collect every result.

algernon_orchestrate — one shot: plan, fan out, and return the plan plus all results.

Install

pip install algernon-mcp       # 0.1.1 — no key? it uses your local Ollama automatically
algernon                       # then add {"command": "algernon"} to your MCP client

Source: github.com/sammyboi81/algernon

Sentarion MCP

Governed orchestration that composes the two above: every dispatch passes a fail-closed two-chamber gate first and is logged to both memory chains. The gate your agents can't bypass.

govern — ask "may I?" before acting; a rendered veto blocks, an unreachable governor never silently approves.

orchestrate_and_record — gate → plan + fan-out → auto-logged to the local and hosted chain.

dispatch_with_dependencies — waves by depends_on; dependents receive {{id}} results.

worktree — governed git-worktree sandbox so fleet work never touches your live checkout.

Install

pip install sentarion-mcp      # 0.2.2
# hosted, no install:
claude mcp add --transport http sentarion https://arkhive.dondatabrain.com/sentarion/mcp

Source: github.com/sammyboi81/sentarion

v2 — the paid upgrade

Everything above stays free. v2 is for teams who run this every day: tenant spaces, full-text recall, token-budgeted context packs, Ed25519-signed verify that names the tampered block, inferred risk flags + per-agent policies, fleet budgets and result cache, {{id}} data flow, MCP progress + background jobs, signed audit manifests, adversarial code review, a worktree sandbox with diffs, and a hosted endpoint with per-key spaces.

Free 14-day v2 trial key → What v2 adds

v2 is included in InboxAxe Pro — $27 for your first 15 days, then $177/mo. Start →

Want it done for you?

All three servers are free forever — self-host, no telemetry. When you'd rather not DIY:

Custom AI agent — $700 flat — a working MCP agent built for your workflow, installed into your Claude or ChatGPT in one call, done-for-you by the founder. Claim a slot →

ArkHive Enterprise — from $2,500 — hand-delivered install + pilot on your own server, with the team that built it. Contact us →

Built by the team behind InboxAxe — the governed AI marketing platform where nothing sends without your yes.

What stays private

These three servers are fully open source and self-hostable. The production DonDataBrain substrate they were grown in — the 2.29M-block flagship chain and the Senthar runtime — is licensed separately. Safety shouldn't be behind a paywall; the safety layer is the part we give away.